Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am Sahithi Nara, an AI engineer and recent data science graduate focused on building end-to-end AI-powered data automation systems. I specialize in architecting agent-based workflows, retrieval-augmented generation, and scalable data pipelines across cloud and on-prem platforms. I have hands-on experience fine-tuning open-source LLMs (LLaMA, Mistral, Falcon, CodeT5), implementing RAG with Pinecone, and deploying production-ready ML/AI solutions using Airflow, Snowflake, and AWS. I'm passionate about applying AI to healthcare, multilingual NLP, and real-time data processing to improve operational efficiency and decision making.…I am Sahithi Nara, an AI engineer and recent data science graduate focused on building end-to-end AI-powered data automation systems. I specialize in architecting agent-based workflows, retrieval-augmented generation, and scalable data pipelines across cloud and on-prem platforms. I have hands-on experience fine-tuning open-source LLMs (LLaMA, Mistral, Falcon, CodeT5), implementing RAG with Pinecone, and deploying production-ready ML/AI solutions using Airflow, Snowflake, and AWS. I'm passionate about applying AI to healthcare, multilingual NLP, and real-time data processing to improve operational efficiency and decision making.

Sahithi Nara

AI Engineer, Data Scientist, Full Stack Developer, +3





I am Sahithi Nara, an AI engineer and recent data science graduate focused on building end-to-end AI-powered data automation systems. I specialize in architecting agent-based workflows, retrieval-augmented generation, and scalable data pipelines across cloud and on-prem platforms. I have hands-on experience fine-tuning open-source LLMs (LLaMA, Mistral, Falcon, CodeT5), implementing RAG with Pinecone, and deploying production-ready ML/AI solutions using Airflow, Snowflake, and AWS. I'm passionate about applying AI to healthcare, multilingual NLP, and real-time data processing to improve operational efficiency and decision making.…I am Sahithi Nara, an AI engineer and recent data science graduate focused on building end-to-end AI-powered data automation systems. I specialize in architecting agent-based workflows, retrieval-augmented generation, and scalable data pipelines across cloud and on-prem platforms. I have hands-on experience fine-tuning open-source LLMs (LLaMA, Mistral, Falcon, CodeT5), implementing RAG with Pinecone, and deploying production-ready ML/AI solutions using Airflow, Snowflake, and AWS. I'm passionate about applying AI to healthcare, multilingual NLP, and real-time data processing to improve operational efficiency and decision making.

Available to hire

I am Sahithi Nara, an AI engineer and recent data science graduate focused on building end-to-end AI-powered data automation systems. I specialize in architecting agent-based workflows, retrieval-augmented generation, and scalable data pipelines across cloud and on-prem platforms.

I have hands-on experience fine-tuning open-source LLMs (LLaMA, Mistral, Falcon, CodeT5), implementing RAG with Pinecone, and deploying production-ready ML/AI solutions using Airflow, Snowflake, and AWS. I’m passionate about applying AI to healthcare, multilingual NLP, and real-time data processing to improve operational efficiency and decision making.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Work Experience

AI & ML Graduate Researcher at San Jose State University

August 1, 2024 - May 1, 2025

Pioneered a zero-touch SDLC automation platform using five autonomous agents simulating software and data engineering lifecycles without manual input. Architected a LangGraph-driven swarm with a Streamlit UI for real-time orchestration and natural language collaboration across engineering pipelines. Fine-tuned LLaMA, Mistral, Falcon, CodeT5 on role-specific tasks using HPC GPUs, optimizing output quality and parallelized execution flows. Engineered RAG workflows with Pinecone for contextual memory and document grounding; built validation pipelines in Airflow and Snowflake. Instrumented 50K+ multi-agent logs for tracking, fallback, and reproducibility, boosting system reliability and task consistency across runs.

Software Engineering Intern at HighRadius Corporation - India

January 1, 2022 - April 1, 2022

Developed Terraform scripts for infrastructure automation; reduced manual provisioning time by 76%. Created end-to-end CI/CD pipelines using GitHub Actions, integrating automated build, test, and deployment workflows to shorten release cycles by 51%. Deployed AWS EC2 instances, configured S3 storage, and managed IAM roles to support production and staging infrastructure. Maintained and monitored Linux-based application servers with customized shell scripts for log rotation and system health monitoring, improving uptime reliability. Wrote internal Python utilities to automate log parsing and perform automated system health checks, reducing troubleshooting time by 29%.

Software Engineer at Srinivasan Software Solutions - India

January 1, 2021 - December 1, 2021

Engineered production infrastructure and ETL workflows on AWS environments using EC2, S3, VPC, IAM and hardened Linux instances for healthcare data in MySQL and Snowflake, achieving 24x7 availability and 99.98% reliability. Automated provisioning and configuration management of 30+ Linux servers using Terraform and Ansible, reducing manual intervention by 88% and eliminating environment drift across dev, staging, and prod pipelines. Built CI/CD workflows with Docker, Kubernetes, and Jenkins to deploy microservices at scale; decreased deployment latency from 15 mins to 1.8 minutes and ensured 61% improvement in rollout consistency.

Software Engineer at Srinivasan Software Solutions

January 1, 2021 - December 1, 2021

Engineered production infrastructure and ETL workflows on AWS environments using EC2, S3, VPC, IAM and hardened Linux instances for healthcare data in MySQL and Snowflake, achieving 24x7 availability and 99.98% reliability. Automated provisioning and configuration management of 30+ Linux servers using Terraform and Ansible, reducing manual intervention by 88% and eliminating environment drift across dev, staging, and prod pipelines. Built CI/CD workflows with Docker, Kubernetes, and Jenkins to deploy microservices at scale; decreased deployment latency from 15 minutes to 1.8 minutes and achieved 61% improvement in rollout consistency.